OpenAI engineer Tibo announced that the 1 million Token context window for the GPT-5.6 Sol model in Codex has been expanded from API key-only access to include ChatGPT account scenarios. Plus, Pro, and other subscription users can manually enable a full context window of nearly 1.05 million Tokens when using the Codex programming agent to retain more code content, suitable for professional scenarios such as large-scale codebase refactoring. However, it should be noted that the model's default context length is the result of comprehensive optimization, and enabling the million-Token context will accelerate subscription quota consumption, so it is recommended to use it only when necessary.